meeting-insights-analyzer

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No credentials, secrets, or sensitive file paths were detected in the skill instructions or examples.
  • [SAFE]: The skill does not perform any external downloads or network requests. It mentions local storage of meeting transcripts to maintain privacy.
  • [SAFE]: No command execution, subprocess spawning, or privilege escalation patterns were identified.
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill is designed to process untrusted data from external transcript files. 1. Ingestion points: Scans and reads local files with extensions .txt, .md, .vtt, .srt, and .docx (SKILL.md). 2. Boundary markers: Absent; there are no instructions to use delimiters or ignore instructions embedded within the transcript text. 3. Capability inventory: Analysis is limited to textual summarization and pattern recognition; no file-writing, network-access, or code-execution capabilities are present in the skill definition. 4. Sanitization: Absent; the skill does not implement validation or escaping of the ingested transcript content. This surface is considered low risk due to the absence of exploitable capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 10:28 AM